Transfer Learning using low-dimensional Representations in Reinforcement Learning
Successful learning of behaviors in Reinforcement Learning (RL) are often learned tabula rasa, requiring many observations and interactions in the environment. Performing this outside of a simulator, in the real world, often becomes infeasible due to the large amount of interactions needed. This has...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
KTH, Robotik, perception och lärande, RPL
2020
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279120 http://nbn-resolving.de/urn:isbn:978-91-7873-593-8 |